metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: Marilyn Monroe, underwater, cartoon in the style of SPNGBB
    output:
      url: images/iA96IH_zauRvPOMm20J4T_5b9e07bbe7614a2aa5de82c63eb9ec52.jpg
  - text: Barack Obama, underwater, cartoon in the style of SPNGBB
    output:
      url: images/H4xYvjkZcd3avn8FPEjPl_24d3c8342237416189dfc0a9f49e39b0.jpg
  - text: Tower Bridge, underwater, cartoon in the style of SPNGBB
    output:
      url: images/Jh57Q1q20eovBXnLZTloY_fa3b02e7dd4545f2903f3bee67a07e24.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: cartoon in the style of SPNGBB
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE

Spongebob

Prompt
Marilyn Monroe, underwater, cartoon in the style of SPNGBB

Prompt
Barack Obama, underwater, cartoon in the style of SPNGBB

Prompt
Tower Bridge, underwater, cartoon in the style of SPNGBB

Model description

Try lowering the LoRA scale if you get distorted results. 0.7 should work well.

Trained using fal-ai/flux-lora-fast-training.

Trigger words

You should use cartoon in the style of SPNGBB to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.